Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It implies a read-only metadata lookup and usefully enumerates the returned sections, but says nothing about behavior for an unknown or misspelled block name (error vs empty result), whether name matching is exact or fuzzy, or result size.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the verb and the returned payload, with no filler. The second sentence is short and adds intent rather than repeating the first.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter, no-output-schema lookup, the enumerated return content does most of the work an output schema would do. The main remaining gap is sibling disambiguation against get_class_info and list_media_blocks.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the blockName parameter is already thoroughly documented with concrete examples and the short-name vs fully-qualified-name note. The description adds no meaning beyond the schema, which is the baseline expectation here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Get detailed information') with a clearly scoped resource ('a specific media block') and enumerates exactly what is returned: properties, methods, events, pads, constructor parameters, and documentation. It does not explicitly contrast itself with the closest sibling, get_class_info, so the distinction between a media block and an SDK class is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use this to understand how to configure and use a specific media block in a pipeline' gives a real usage context, but there are no exclusions or named alternatives (list_media_blocks for discovery, get_class_info for non-block classes), so an agent must infer the routing itself.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.